Audio Expert

About this role

skilled music transcription experts to support an AI training project focused on polyphonic audio analysis, SATB transcription, music notation, MusicXML, and Python. The role involves reconstructing accurate musical scores from mixed audio recordings, separating simultaneous vocal lines, identifying pitch and rhythm information, and validating the final notation for musical and technical correctness. This opportunity is intended for candidates with strong ear training, notation knowledge, and technical problem-solving ability rather than general audio-production or speech-transcription backgrounds. Relevant expertise is valued more than formal education or a specific number of years of experience.

Music Transcription AI Expert

Responsibilities

• Transcribe polyphonic recordings into structured notation while separating soprano, alto, tenor, and bass lines from mixed audio.
• Identify pitches, onsets, durations, rests, re-articulations, rhythmic grids, key signatures, accidentals, and enharmonic spelling.
• Generate, manipulate, and validate MusicXML scores using musical review, structured checks, or resynthesis.
• Use Python and audio-analysis tools to inspect recordings, analyze spectral information, and automate parts of the transcription workflow.

Qualifications

• Strong Python programming ability combined with advanced ear training and polyphonic music-transcription skills.
• Strong understanding of harmony, rhythm, voice leading, SATB writing, and standard musical notation.
• Experience with choral arranging, score preparation, composition, performance, research, or closely related polyphonic transcription work.
• Ability to produce accurate, reproducible notation while diagnosing subtle musical and technical errors.